Back to skill

Security audit

clawtip-sauron

Security checks for vulnerabilities and agentic risk

Overview

The skill is rated suspicious because a scanner reports that remote order numbers can escape the local storage folder and overwrite writable JSON files; the review is incomplete because some references could not be resolved.

Treat this as a review-needed skill. Before installing, consider whether you trust it with access to files the agent can write, since the reported path issue could overwrite a JSON file outside its order folder. The scan is incomplete: although all listed components were scanned, some references could not be resolved, so this assessment does not establish that the skill is safe.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/file_utils.py
Finding

Remote order numbers escape the local order-storage directory

Content
View full analysis

Impact

An orderNo such as '../../../../audit-target' resolves to ~/audit-target.json on Linux/macOS. The script creates or truncates that file with the agent's permissions. Existing writable JSON configuration or other application state can therefore be overwritten when their parent directories exist. The .json suffix and structured document limit the write; arbitrary code execution is not established.

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read, file_write, network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.